NVIDIA NIM
Catatan dari sumber
Free with NVIDIA Developer Program membership. 100+ models. Rate-limited per model.
Setup dalam 5 menit
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://integrate.api.nvidia.com/v1",
apiKey: process.env.NVIDIA_NIM_API_KEY,
});
const response = await client.chat.completions.create({
model: "deepseek-ai-deepseek-v4-1-flash",
messages: [{ role: "user", content: "Halo!" }],
});
console.log(response.choices[0].message.content);NVIDIA_NIM_API_KEY=your-api-key-hereBelum punya API key? Ambil di halaman resmi NVIDIA NIM ↗.
Cara claim API key gratis
Langkah umum — detail pastinya ikutin halaman resmi NVIDIA NIM.
- 1.Buka halaman API key NVIDIA NIM ↗
- 2.Daftar akun baru, atau login kalau udah punya.
- 3.Generate API key di dashboard / settings.
- 4.Pakai API key + Base URL
https://integrate.api.nvidia.com/v1di SDK atau HTTP client.
Model tersedia (82+)
- Modality
- text + image + reasoning
- Context
- 1.0M
- Rate limit
- Up to 40 RPM
- Modality
- text + image + video + reasoning
- Context
- 1.0M
- Rate limit
- Up to 40 RPM
- Modality
- vision + reasoning
- Context
- 1.0M
- Modality
- Text
- Context
- 1M
- Output
- 262K
- Rate limit
- 40 RPM, 10,000 RPD
- Modality
- text + image + reasoning
- Context
- 1.0M
- Rate limit
- Up to 40 RPM
- Modality
- text + reasoning
- Context
- 1.0M
- Output
- 128K
- Rate limit
- Up to 40 RPM
- Modality
- text + image + video + pdf + reasoning
- Context
- 1.0M
- Output
- 128K
- Rate limit
- Up to 40 RPM
- Modality
- Text + Image + Video
- Context
- 262K
- Output
- 8K
- Rate limit
- 40 RPM, 10,000 RPD
| Model | Modality | Context | Output | Rate limit |
|---|---|---|---|---|
deepseek-ai/deepseek-v4.1-flash deepseek-ai-deepseek-v4-1-flash | text + image + reasoning | 1.0M | Up to 40 RPM | |
minimaxai/minimax-m3.1-flash minimaxai-minimax-m3-1-flash | text + image + video + reasoning | 1.0M | Up to 40 RPM | |
Nemotron 3.5 Super VL 120B A12B nemotron-3-5-super-vl-120b-a12b | vision + reasoning | 1.0M | ||
nvidia/nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | Text | 1M | 262K | 40 RPM, 10,000 RPD |
stepfun-ai/step-5-preview stepfun-ai-step-5-preview | text + image + reasoning | 1.0M | Up to 40 RPM | |
z-ai/glm-5.3 z-ai-glm-5-3 | text + reasoning | 1.0M | 128K | Up to 40 RPM |
z-ai/glm-5.3-flash z-ai-glm-5-3-flash | text + image + video + pdf + reasoning | 1.0M | 128K | Up to 40 RPM |
google/gemma-4-31b-it google/gemma-4-31b-it | Text + Image + Video | 262K | 8K | 40 RPM, 10,000 RPD |
+ 92 more models model lainnya — lihat daftar lengkap di sumber.
Model ini di provider lain (12)
Nama model yang sama juga muncul di provider lain menurut sumber masing-masing — versi/kuantisasi bisa beda.
- openai/gpt-oss-20b· 6 provider
- z-ai/glm-5.3-flash· 4 provider
- deepseek-ai/deepseek-v4.1-flash· 3 provider
- google/gemma-4-31b-it· 3 provider
- z-ai/glm-5.3· 3 provider
- moonshotai/kimi-k2.6· 3 provider
- poolside/laguna-xs-2.1· 3 provider
- nvidia/nemotron-3.5-content-safety· 3 provider
- Nemotron 3 Super 120B A12B· 3 provider
- nvidia/nemotron-3.5-lightning-30b-a3b· 2 provider
- Nemotron 3 Nano Omni 30B A3B Reasoning· 2 provider
- nvidia/nemotron-3-ultra-550b-a55b· 2 provider
FAQ
Apakah API NVIDIA NIM gratis?
Ya — menurut sumber: "Free with NVIDIA Developer Program membership. 100+ models. Rate-limited per model." Data dari mnfst/awesome-free-llm-apis, freellm.net, models.dev, terakhir di-sync 28 Okt 2026 — cek sumber untuk kondisi terbaru.
Ada berapa model gratis di NVIDIA NIM?
82 model tercantum per 28 Okt 2026, termasuk deepseek-ai/deepseek-v4.1-flash, minimaxai/minimax-m3.1-flash, Nemotron 3.5 Super VL 120B A12B.
Berapa rate limit NVIDIA NIM?
Beda-beda per model, contoh: deepseek-ai/deepseek-v4.1-flash: Up to 40 RPM; minimaxai/minimax-m3.1-flash: Up to 40 RPM; nvidia/nemotron-3-ultra-550b-a55b: 40 RPM, 10,000 RPD. Limit lengkap per model, lihat tabel di atas.
Berapa context window maksimal di NVIDIA NIM?
1M (nvidia/nemotron-3-ultra-550b-a55b).